Product Manager, AI Inference Platform

Baseten; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Competitive equity & compensation

US medical/dental/vision coverage for

Flexible PTO including Winter Break

Paid parental leave

Fertility & family-building stipend

401(k) plan

Exposure to ML startups & networking

Job summary

Baseten is hiring a Product Manager to own the experience of building on Baseten, from discovering and evaluating models to deploying, optimizing, and operating them in production.

You will shape products including Model APIs, Dedicated Inference, Model Evaluations, and our Model Library, collaborating with engineering, research, and GTM to deliver outcomes developers love and businesses rely on.

Qualifications

• 10+ years building and shipping AI/ML products or platforms.
• A technical background in software engineering, ML engineering, research, or equivalent hands-on experience.
• Direct experience building or deploying models using technologies like PyTorch, TensorRT-LLM, vLLM, SGLang, NVIDIA Dynamo, or similar frameworks.
• Strong understanding of model serving, GPU economics, and the tradeoffs between quality, latency, throughput, and cost.
• Exceptional developer product instincts. You know how to make complex technology approachable without sacrificing power.
• A track record of leading cross-functional product initiatives and turning technical capabilities into measurable adoption or revenue growth.

Responsibilities

• Own product strategy and roadmap across Baseten's inference offerings, with a focus on developer adoption and business impact.
• Make it easier for developers to discover, evaluate, deploy, and manage AI models through our APIs, SDKs, CLI, and console.
• Work with inference engineers and researchers to turn technical advances into compelling customer-facing capabilities.
• Help determine which models, workloads, and customer needs we prioritize.
• Partner with GTM and leadership on pricing, packaging, launches, and commercialization.
• Spend time with developers and customers to understand what's working, what's frustrating, and what we should build next.

Skills

AI/ML product leadership

Cross-functional collaboration

Technical background

Developer empathy

Product strategy

Tools

PyTorch

TensorRT-LLM

vLLM

SGLang

NVIDIA Dynamo

Job description

Baseten is hiring a Product Manager to own the experience of building on Baseten, from discovering and evaluating models to deploying, optimizing, and operating them in production.

You will shape products including Model APIs, Dedicated Inference, Model Evaluations, and our Model Library, collaborating with engineering, research, and GTM to deliver outcomes developers love and businesses rely on.